src/data_fetch.py

"""Fetch latest hourly ETH data via CCXT — ready for V5 feature pipeline"""
import ccxt # type: ignore
import pandas as pd
from datetime import datetime
from src.config import SYMBOL, TIMEFRAME

def fetch_latest_data(limit: int = 2000) -> pd.DataFrame:
    """Returns hourly OHLCV + placeholder on-chain columns (exactly as notebook)"""
    exchange = ccxt.binance({'enableRateLimit': True})
    
    print(f"📡 Fetching latest {TIMEFRAME} ETH data from Binance...")
    ohlcv = exchange.fetch_ohlcv(SYMBOL, timeframe=TIMEFRAME, limit=limit)
    
    df = pd.DataFrame(ohlcv, columns=['timestamp', 'open', 'high', 'low', 'close', 'volume'])
    df['timestamp'] = pd.to_datetime(df['timestamp'], unit='ms')
    df = df.set_index('timestamp').sort_index()
    df['return'] = df['close'].pct_change().fillna(0.0)
    
    # Placeholder on-chain (same scaling as original dataset)
    df['tx_count'] = df['volume'] * 1.5
    df['active_senders'] = df['volume'] * 0.8
    df['active_receivers'] = df['volume'] * 0.7
    df['total_eth_transferred'] = df['volume'] * 1.2
    df['total_gas_used'] = df['volume'] * 0.9
    
    print(f"✅ Fetched {len(df)} hourly bars (up to {df.index[-1]})")
    return df